© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 32674
    Prev
    Next
    INDEX
    Explanations

    early career years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸İä¹ĭ
    -0.08
    转è¿ĩ
    -0.07
    åİ»ä½ķ
    -0.07
    edah
    -0.07
    èĮĥæĸĩç½ij
    -0.07
    åĪ«ç¦»
    -0.07
    retto
    -0.07
    EventListener
    -0.07
    éģĵæĿ¥
    -0.07
    çļĦè¿Ļ个
    -0.07
    POSITIVE LOGITS
    éĺ¶æ®µ
    0.08
    aip
    0.07
    eger
    0.07
    ail
    0.07
    å±ĤéĿ¢
    0.07
    æľĢæĺ¯
    0.07
    èĤ¯å®ļè¦ģ
    0.07
    æĪ²
    0.07
     lay
    0.06
     stage
    0.06
    Activations Density 0.080%

    No Known Activations